Multi-Parameter Water Quality Inversion in Heterogeneous Inland Waters Using UAV-Based Hyperspectral Data and Deep Learning Methods
Open Access
- 25 June 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (13) , 2191
Abstract
Water quality monitoring is crucial for ecological protection and water resource management. However, traditional monitoring methods suffer from limitations in temporal, spatial, and spectral resolution, which constrain the effective evaluation of urban rivers and multi-scale aquatic systems. To address challenges such as ecological heterogeneity, multi-scale complexity, and data noise, this paper proposes a deep learning framework, TL-Net, based on unmanned aerial vehicle (UAV) hyperspectral imagery, to estimate four water quality parameters: total nitrogen (TN), dissolved oxygen (DO), total suspended solids (TSS), and chlorophyll a (Chla); and to produce their spatial distribution maps. This framework integrates Transformer and long short-term memory (LSTM) networks, introduces a cross-temporal attention mechanism to enhance feature correlation, and incorporates an adaptive feature fusion module for dynamically weighted integration of local and global information. The experimental results demonstrate that TL-Net markedly outperforms conventional machine learning approaches, delivering consistently high predictive accuracy across all evaluated water quality parameters. Specifically, the model achieves an R2 of 0.9938 for TN, a mean absolute error (MAE) of 0.0728 for DO, a root mean square error (RMSE) of 0.3881 for total TSS, and a mean absolute percentage error (MAPE) as low as 0.2568% for Chla. A spatial analysis reveals significant heterogeneity in water quality distribution across the study area, with natural water bodies exhibiting relatively uniform conditions, while the concentrations of TN and TSS are substantially elevated in aquaculture areas due to aquaculture activities. Overall, TL-Net significantly improves multi-parameter water quality prediction, captures fine-scale spatial variability, and offers a robust and scalable solution for inland aquatic ecosystem monitoring.Keywords
Funding Information
- Special Fund for Science and Technology Plan of Jiangsu Province (BE2022385, 72174079, CG2323, CG2436, 2022-29)
- National Natural Science Foundation of China (BE2022385, 72174079, CG2323, CG2436, 2022-29)
- Key Research and Development Plan of Lianyungang City (BE2022385, 72174079, CG2323, CG2436, 2022-29)
- Excellent Teaching Team of Qinglan Project in Jiangsu Province (BE2022385, 72174079, CG2323, CG2436, 2022-29)
This publication has 41 references indexed in Scilit:
- Assessing water quality environmental grades using hyperspectral images and a deep learning model: A case study in Jiangsu, ChinaEcological Informatics, 2024
- Monitoring water quality parameters of freshwater aquaculture ponds using UAV-based multispectral imagesEcological Indicators, 2024
- Arbitrary-scale Super-resolution via Deep Learning: A Comprehensive SurveyInformation Fusion, 2023
- Remote sensing inversion of water quality parameters in the Yellow River DeltaEcological Indicators, 2023
- A novel selective learning based transformer encoder architecture with enhanced word representationApplied Intelligence, 2022
- Estimating Chemical Oxygen Demand in estuarine urban rivers using unmanned aerial vehicle hyperspectral imagesEcological Indicators, 2022
- Machine learning-based inversion of water quality parameters in typical reach of the urban river by UAV multispectral dataEcological Indicators, 2021
- Deep learning based regression for optically inactive inland water quality parameter estimation using airborne hyperspectral imageryEnvironmental Pollution, 2021
- Various dimension reduction techniques for high dimensional data analysis: a reviewArtificial Intelligence Review, 2021
- Monitoring inland water quality using remote sensing: potential and limitations of spectral indices, bio-optical simulations, machine learning, and cloud computingEarth-Science Reviews, 2020